Comfy-agent curated_wan_2_2_i2v_14b_gguf_with_lora_included

install

source · Clone the upstream repo

git clone https://github.com/steliosot/comfy-agent

Claude Code · Install into ~/.claude/skills/

T=$(mktemp -d) && git clone --depth=1 https://github.com/steliosot/comfy-agent "$T" && mkdir -p ~/.claude/skills && cp -r "$T/skills/workflows/video_t2v_i2v_avatar/curated_wan_2_2_i2v_14b_gguf_with_lora_included" ~/.claude/skills/steliosot-comfy-agent-curated-wan-2-2-i2v-14b-gguf-with-lora-included && rm -rf "$T"

manifest: skills/workflows/video_t2v_i2v_avatar/curated_wan_2_2_i2v_14b_gguf_with_lora_included/SKILL.md

source content

curated_wan_2_2_i2v_14b_gguf_with_lora_included

Curated workflow skill generated from

Wan 2.2 I2V 14b GGUF with Lora Included.json

Capability Family

```
video_t2v_i2v_avatar
```

Inputs

Optional runtime overrides supported by

run(...)

```
prompt
```
```
negative_prompt
```
```
width
```
,
```
height
```
```
seed
```
,
```
steps
```
,
```
cfg
```
```
sampler_name
```
,
```
scheduler
```
,
```
denoise
```
```
server
```
,
```
headers
```
,
```
api_prefix
```

Outputs

Returns JSON with:
- ```
status
```
- ```
prompt_id
```
- ```
output_images
```
  (includes image/video entries reported by Comfy history)

Model Requirements

```
vae
```
:
```
wan_2.1_vae.safetensors
```
->
```
models/vae
```

clip

umt5_xxl_fp8_e4m3fn_scaled.safetensors

models/clip

diffusion_model

wan2.2_i2v_A14b_high_noise_lightx2v_4step-Q6_K.gguf

models/diffusion_models

diffusion_model

wan2.2_i2v_A14b_low_noise_lightx2v_4step-Q6_K.gguf

models/diffusion_models

Custom Node Requirements

```
ComfyUI-GGUF
```
```
comfyui-videohelpersuite
```

Links Extracted From Workflow Notes

Source

Original:

comfy-data/workflows/Wan 2.2 I2V 14b GGUF with Lora Included.json

Routing Metadata

Family:
```
video_t2v_i2v_avatar
```
Input modalities:
```
image, text_prompt
```
Output modalities:
```
video/mp4
```
Model families:
```
sd3, wan
```
Node count:
```
18
```
Complexity score:
```
9
```
Resource profile:
```
very_high
```

Estimated runtime:

heavy (can exceed 6 min; best on high-VRAM GPU)

Max latent resolution hint:
```
None
```
x
```
None
```
Max sampler steps hint:
```
None
```

Detected Models

```
vae
```
:
```
wan_2.1_vae.safetensors
```
->
```
models/vae
```

clip

umt5_xxl_fp8_e4m3fn_scaled.safetensors

models/clip

diffusion_model

wan2.2_i2v_A14b_high_noise_lightx2v_4step-Q6_K.gguf

models/diffusion_models

diffusion_model

wan2.2_i2v_A14b_low_noise_lightx2v_4step-Q6_K.gguf

models/diffusion_models

Detected Custom Nodes

```
ComfyUI-GGUF
```
```
comfyui-videohelpersuite
```

Runtime Warnings

Large model(s) detected; ensure enough VRAM and disk space.
Uses custom nodes; missing nodes can cause validation/runtime failures.
Video workflow: usually slower and VRAM-intensive than still-image workflows.